JP6687266B1 - Elevator control system, its control method and program - Google Patents

Abstract

To reduce the waiting time. An elevator control system includes a photographing means for photographing a boarding / alighting candidate who gets in and out of an elevator of a building, and an image authentication of the boarding / alighting candidate based on a photographed image photographed by the photographing means to obtain a boarding / alighting candidate. The learning means for learning the recognition means for recognizing, and the learning pattern for each entry / exit candidate of the entry / exit candidate's movement pattern to each floor in which the recognition result of the recognition means and the time information of entry / exit are associated. Control means for controlling the movement of the elevator based on the movement pattern. The learning means searches for a boarding / alighting candidate who will board the elevator before and after the current time based on the movement pattern, and determines a floor on which the searched boarding / alighting candidate is boarding as a floor on which the elevator cage is on standby. The control means performs control to move the elevator car to the floor determined by the learning means and make it stand by. [Selection diagram] Figure 1

Description

  The present invention relates to an elevator control system for controlling an elevator, a control method therefor, and a program.

  Waiting time for elevators is very stressful in the modern society, which is busy every minute. Depending on the building, it is possible to shorten the travel time by limiting the destination floor that can be moved in an environment where multiple elevators are installed, such as low floors, high floors, odd / even floors, and VIPs. . However, by limiting the destination floors that can be moved, there is a problem in that the elevator is not in operation for a long time and conversely the waiting time is long.

  In order to reduce such a waiting time, an elevator control system is known in which the elevator is moved to an optimum place and put on standby based on the past usage data of the elevator (for example, refer to Patent Document 1).

JP, 2009-274871, A

  An object of the present disclosure is to provide an elevator control system, a control method therefor, and a program that solve any of the problems described above.

One aspect of the present invention for achieving the above object is
A photographing means for photographing the passengers getting on and off the elevator of the building,
Recognition means for recognizing the boarding / alighting candidate by performing image authentication of the boarding / alighting candidate based on the image taken by the imaging means;
Learning means for learning, for each of the boarding / alighting candidates, a movement pattern of the boarding / alighting candidate associated with the recognition result of the recognition means and the time information of the boarding / alighting, for each of the boarding / alighting candidates.
A control means for controlling the movement of the elevator based on the movement pattern learned by the learning means,
Based on the movement pattern, the learning unit searches for a boarding / alighting candidate who is boarding the elevator before and after the current time, and determines a floor on which the searched boarding / alighting candidate is boarding, as a floor for waiting the elevator cage,
The control means moves the elevator car to the floor determined by the learning means, and performs control to make it stand by,
The elevator control system is characterized by the following.
One aspect of the present invention for achieving the above object is
A step of shooting a boarding / alighting candidate who gets on and off the elevator of the building,
Recognizing the boarding / alighting candidate by performing image authentication of the boarding / alighting candidate based on the photographed image taken,
A step of learning, for each of the boarding / alighting candidates, a movement pattern of the boarding / alighting candidate to each floor in which the recognition result and the time information of the boarding / alighting are associated with each other;
Based on the movement pattern, a search for a boarding / alighting candidate to board the elevator before and after the current time, and a floor on which the boarding / alighting candidate found boarding is determined as a floor where the elevator cage is waiting,
Moving the elevator car to the determined floor, and performing a control of waiting.
The elevator control method is characterized by including.
One aspect of the present invention for achieving the above object is
A process of recognizing the boarding / alighting candidate by performing image authentication of the boarding / alighting candidate based on a captured image of the boarding / alighting candidate who gets on and off the elevator of the building,
A process of learning, for each of the boarding / alighting candidates, a movement pattern of the boarding / alighting candidate associated with the recognition result and the time information of the boarding / alighting, to each floor.
Based on the movement pattern, a search for the boarding / alighting candidates to board the elevator before and after the current time, the floor on which the searched boarding / alighting candidates board, is determined as a floor where the elevator cage is waiting,
A process of moving the elevator car to the determined floor and performing control to make it stand by,
Is a program for an elevator control system characterized by causing a computer to execute.

  According to the present disclosure, it is possible to provide an elevator control system, a control method thereof, and a program that solve any of the problems described above.

It is a block diagram showing a schematic structure of an elevator control system concerning one embodiment of the present invention. It is a figure which shows the imaging | photography part provided in the EV hall and elevator cage of each floor. It is a figure which shows the imaging | photography part arrange | positioned at the elevator hall of each floor. It is a figure which shows the imaging part arrange | positioned in an elevator cage. It is a flow chart which shows a rough learning flow of AI server. It is a flowchart which shows the flow of the acquisition method of the information of a movement pattern. It is a figure which shows an example of the information of a movement pattern. It is a flow chart which shows the flow of the control method of the elevator control system concerning one embodiment of the present invention.

Embodiments of the present invention will be described below with reference to the drawings.
An elevator control system according to an embodiment of the present invention is a system installed in a predetermined building and capable of shortening the waiting time of an elevator getting on / off candidate. The predetermined building is, for example, a hotel, a condominium, a public office building, an office building, or the like in which only a limited number of people can enter, and is a building to which an entrance method using image authentication such as face authentication is introduced.

  FIG. 1 is a block diagram showing a schematic configuration of an elevator control system according to this embodiment. The elevator control system 1 according to the present embodiment includes a photographing unit 2 that photographs a boarding / alighting candidate, an authentication server 3 that performs image authentication of a boarding / alighting candidate, and an AI server 4 that learns a movement pattern of a boarding / alighting candidate to each floor. And an elevator control unit 5 that controls the elevation of the elevator cage.

  The image capturing unit 2 is a specific example of image capturing means. The image capturing unit 2 is, for example, a camera that can capture a still image or a moving image. The image capturing unit 2 may have a function of playing a registered voice.

  As shown in FIG. 2, the imaging unit 2 is provided in each of the elevator (EV) hall and the elevator car 10 on each floor. As shown in FIG. 3, the imaging unit 2 of the elevator hall on each floor is installed near the entrance / exit of the elevator cage 10 and is capable of imaging the face of the entry / exit candidate of the elevator cage 10. Further, as shown in FIG. 4, the imaging unit 2 in the elevator cage 10 is installed near the door of the elevator cage 10 and can image the face of the entry / exit candidate in the elevator cage 10. Each image capturing unit 2 transmits the captured face image of the boarding / alighting candidate to the authentication server 3.

  The authentication server 3 is a specific example of a recognition unit. The authentication server 3 performs face authentication of the boarding / alighting candidate based on the face image of the boarding / alighting candidate sent from each imaging unit 2, and determines whether or not the boarding / alighting candidate is a previously registered person.

  The authentication server 3 performs face authentication when the boarding / alighting candidate boards the elevator cage 10 and gets off the elevator cage 10 based on the face image of the boarding / alighting candidate transmitted from each imaging unit 2.

  The authentication server 3 transmits to the AI server 4 the information (ID information and the like) of the authenticated boarding / alighting candidate as well as the position information indicating which image capturing unit 2 was used for image capturing and the time information indicating the time of image capturing.

  An AI (artificial intelligence) server is a specific example of learning means. The AI server 4 is composed of, for example, a learning device such as a neural network and performs deep learning. The AI server 4 learns the movement pattern of the boarding / alighting candidate to each floor.

  The AI server 4 stores, for each boarding / alighting candidate, information on the boarding / alighting candidate, position information, and time information transmitted from the authentication server 3. The AI server 4 uses the information of the boarding / alighting candidates for each boarding / alighting candidate stored, the position information, and the time information of each boarding / alighting candidate of each boarding / alighting candidate indicating which floor to move to which floor. Learn movement patterns. The AI server 4, for example, learns the movement pattern of each boarding / alighting candidate until the boarding time of each boarding / alighting candidate reaches a predetermined time or more or the number of boarding times reaches a predetermined number of times or more.

  The AI server 4 issues an instruction signal for instructing on which floor the elevator cage 10 is to be on standby in an idle time when the elevator is not called, based on the learned movement patterns of the entry / exit candidates. Send to 5. The AI server 4 may transmit an instruction signal to the elevator control unit 5 based on the statistical information of the time zone that statistically indicates which candidate is boarding the elevator at which floor at each time.

  The elevator control unit 5 is a specific example of control means. The elevator control unit 5 controls the elevator cage 10 to move up and down to the called floor in response to the operation of a call button (up / down button) provided near the elevator doors on each floor.

  The elevator control unit 5 controls the elevator car 10 to move up and down to the designated destination floor in response to the operation of the destination floor button provided near the door in the elevator cage 10. Further, the elevator control unit 5 raises and lowers the elevator cage 10 to the floor designated by the instruction signal in response to the instruction signal from the AI server 4 in a free time period when the call button is not pressed, and the elevator cage 10 at the floor. The control for making the cage 10 stand by is performed.

  The elevator control unit 5 includes, for example, a CPU (Central Processing Unit) that performs control processing, arithmetic processing, and the like, a ROM (Read Only Memory) and a RAM (Random RAM) that store a control program executed by the CPU, an arithmetic program, and the like. The memory is mainly composed of a microcomputer including a memory including an access memory and an interface unit (I / F) that inputs and outputs signals to and from the outside. The CPU, memory, and interface unit are connected to each other via a data bus or the like.

  By the way, the waiting time of the elevator is very stressful in the modern society, and it is desired to reduce the waiting time.

  On the other hand, as described above, the elevator control system 1 according to the present embodiment detects the boarding / alighting candidate by performing the face authentication of the boarding / alighting candidate based on the imaged image of the boarding / alighting candidate. The authentication server 3 that recognizes an image, the AI server 4 that learns the movement pattern in which the recognition result of the authentication server 3 is associated with the boarding / alighting time information of the boarding / alighting candidate for each boarding / alighting candidate, and the learned moving pattern. And an elevator control unit 5 that controls the movement of the elevator. Based on the movement pattern, the AI server 4 searches for a boarding / alighting candidate who will board the elevator before and after a predetermined time, and determines the floor on which the searched boarding / alighting candidate is boarding to be the floor on which the elevator cage 10 is waiting. The elevator control unit 5 controls the elevator cage 10 to move to the floor determined by the AI server 4 and wait.

  As a result, the elevator cage 10 can be made to stand by in a timely manner during the time slot in which the boarding / alighting candidate is predicted to board. Therefore, the waiting time of the elevator can be shortened, and the valuable time of many people can be saved. As it is said that if dust accumulates, it will become a mountain, so if you consider the number of users × number of movements × number of days in a year, you can save a lot of time.

FIG. 5 is a flowchart showing a schematic learning flow of the AI server.
The AI server 4 performs learning in the elevator normal operation mode (step S501). The AI server 4 accumulates data on the movement patterns of the entry / exit candidates (step S502). The AI server 4 predicts the floor on which the elevator car 10 will be on standby by using the learned movement pattern data (step S503). The AI server 4 accumulates the predicted floor information and evaluates the result (step S504).

  When the prediction is wrong, the AI server 4 accumulates and analyzes the result of the prediction failure. For example, the AI server 4 detects a difference between the data when the prediction does not hit and the data when the prediction hits, and analyzes the data based on the data to determine whether the data is unique. The AI server 4 reviews the conditions and again predicts the floor on which the elevator car 10 will be on standby by a different method.

  The AI server 4 changes the changeable parameter or finds a new viewpoint from the accumulated data and adds it to the condition, thereby rotating the PDCA cycle and improving the prediction accuracy. Then, the AI server 4 is optimized so as to have an elevator control algorithm more suitable for the building.

  FIG. 6 is a flowchart showing the flow of a method of acquiring movement pattern information. As a precondition, it is assumed that all persons who can use the elevator are registered in advance in the authentication server 3 as entry / exit candidates. It is assumed that a person who is not registered in the authentication server 3 is judged to have a security risk and that floor movement is prohibited.

  For example, the imaging unit 2 on the first floor captures the person A and sends the captured image to the authentication server 3 (step S601).

  The authentication server 3 detects face data from the photographed image transmitted from the photographing unit 2 and determines whether or not the person is a registered entry / exit candidate (step S602).

  When the authentication server 3 determines that the registered face data does not match the face data of the captured image and is not a registered entry / exit candidate (NO in step S602), the authentication server 3 determines that there is a security risk (step S603).

  The authentication server 3 transmits the security risk determination result to the elevator control unit 5 to the elevator control unit 5. When the person A is in front of the door of the elevator, the elevator control unit 5 performs control so that the door is not opened. Further, the authentication server 3 transmits a warning signal to the image capturing unit 2. In response to the warning signal from the authentication server 3, the imaging unit 2 outputs, for example, a voice such as "only an authorized person can get on this elevator" to the person A.

  When the authentication server 3 determines that the registered face data matches the face data of the captured image and is a registered entry / exit candidate (YES in step S602), the information and position information of the authenticated person A ( Information on the boarding floor of the elevator hall) and time information is transmitted to the AI server 4 (step S604). The AI server 4 stores the information of the person A, the position information, and the time information transmitted from the authentication server 3.

  The person A operates the call button to call the elevator cage 10 and gets on the elevator cage 10 (step S605).

  The photographing unit 2 in the elevator cage 10 photographs the person A, and the authentication server 3 transmits to the AI server 4 the time information when the person A entered the elevator cage 10 based on the photographed image. The AI server 4 stores the time information when the person A entered the elevator car 10 (step S606).

  When the person A operates the button on the destination floor, the elevator control unit 5 controls the elevator car 10 to move up and down to the destination floor (step S607).

  When the person A gets off from the elevator cage 10, the AI server 4 arrives at the person A based on the image captured by the image capturing unit 2 in the elevator cage 10 and the control information of the elevator cage 10 by the elevator control unit 5. The floor and time information is stored (step S608).

  By the processing shown in FIG. 6, the AI server 4 can collect the information on the movement pattern as shown in FIG. 7, for example. The movement pattern shown in FIG. 7 is an example of elevator usage information for a certain day. The vertical column describes information about three persons A, B, and C, and is collected for each person.

  The authentication server 3 sets the time when the face authentication of the entry / exit candidate before boarding is performed as the arrival time of the elevator (EV) hall, which is the movement source, based on the image captured by the image capturing unit 2 of the elevator hall on each floor.

  The difference between the arrival time of the EV hall and the boarding time of the EV cage boarding the EV cage is the EV waiting time (e) in the EV hall. The difference between the EV cage boarding time and the EV cage disembarking time when getting off from the EV cage is the staying time (f) in the EV cage.

  It is also possible to calculate the travel time of an EV that takes one floor from the source floor and the destination floor. By adding the EV waiting time (e) and the staying time in the EV cage (f), the total traveling time (ki) in the EV traveling can be obtained. When there are a plurality of EVs, data is acquired for each EV like EV1 and EV2.

  Next, how to use the collected information of the AI server 4 will be described. For the sake of simple explanation, it is assumed that this is all movement records, though FIG. 6 is information with extremely few users. The AI server 4 can analyze the movement tendency by learning the movement patterns of the persons A, B, and C.

  For example, as a result of the analysis, it is assumed that the persons A, B, and C come to work earlier in the order of A> B> C. The first floor is the entrance floor, and the seat of person A is on the office floor on the third floor. Similarly, the person B's own seat is on the 11th floor office floor, and the person C's own seat is on the 25th floor office floor. There is a dining room on the 8th floor, and person A eats outside the building at lunch. Person B uses the company cafeteria on the 8th floor, and person C brings a lunch.

  Suppose you go home in the same order A> B> C as when you came to work. In order to reduce the waiting time of the elevator, the elevator cage 10 may be moved and made to stand by in advance as follows, for example, based on the analysis result before the call button of the elevator hall on each floor is operated. .

  During the morning hours, the elevator cage 10 waits on the first floor ⇒ moves to the third floor, waits on the first floor ⇒ moves to the 11th floor, waits on the first floor ⇒ moves to the 25th floor. During the daytime, the elevator cage 10 waits on the 11th floor ⇒ moves to the 8th floor, waits on the 3rd floor ⇒ moves to the 1st floor, waits on the 8th floor ⇒ moves to the 11th floor, waits on the 1st floor ⇒ moves to the 8th floor. During the evening hours, the elevator cage 10 waits on the 3rd floor ⇒ moves to the 1st floor, waits on the 11th floor ⇒ moves to the 1st floor, waits on the 25th floor ⇒ moves to the 1st floor.

  As described above, the elevator control unit 5 can move all the EV waiting times (e) shown in FIG. 6 to 0 minutes by moving the elevator cage 10 in advance and making it stand by. The waiting time of 38 minutes can be reduced.

  Subsequently, a control method of the elevator control system according to the present embodiment will be described. FIG. 8 is a flowchart showing the flow of the control method of the elevator control system according to this embodiment.

  The elevator control unit 5 determines whether there is a person in the elevator hall on each floor based on the captured image captured by the imaging unit 2 on each floor (step S801).

  When it is determined that there is a person in the elevator hall of each floor (YES in step S801), the elevator control unit 5 controls the elevator cage 10 to move up and down to the floor that is called in response to the operation of the call button of each floor. (Step S802).

  If the elevator control unit 5 determines that there is no person in the elevator hall on each floor (NO in step S801), the AI server 4 starts prediction (step S803).

  The AI server 4 searches for the boarding / alighting candidates who board the elevator five minutes before and after the current time based on the stored movement patterns of the boarding / alighting candidates (step S804).

  In addition, if the AI server 4 fails to search for the boarding / alighting candidates who board the elevator within 5 minutes before and after the current time, it further searches for the boarding / alighting candidates for boarding the elevator within 10 minutes before and after the current time. May be. In addition, the AI server 4 is different from usual in the operation of another pattern based on the authentication data transmitted from the authentication server 3 when the retrieved entry / exit candidate is not in the building today, for example, due to vacation or going out. If you're on the floor, you may want to check.

  When the AI server 4 is able to search for the boarding / alighting candidate to board the elevator, the AI server 4 determines whether or not the searched boarding / alighting candidate is one (step S805).

  When the AI server 4 determines that the retrieved entry / exit candidate is one (YES in step S805), the floor where the elevator cage 10 waits for the retrieved entry / exit candidate's floor (hereinafter, elevator cage standby floor). And the determined elevator car waiting floor is output to the elevator controller 5 (step S806).

  On the other hand, when the AI server 4 determines that the retrieved entry / exit candidates are plural (NO in step S805), the floors on which the entry / exit candidates are boarded are arranged in descending order of the number of entry / exit candidates boarding the elevator. The floor with the largest number of entry / exit candidates boarding the elevator is determined as the elevator cage standby floor and output to the elevator controller 5 (step S807).

  It should be noted that the AI server 4 determines, when there are a plurality of floors having the largest number of passengers boarding / alighting in the elevator, the floor that has been the most moved destination in the time zone in the past as the elevator cage waiting floor. Good.

  The elevator control unit 5 moves the elevator cage 10 to the elevator cage standby floor output from the AI server 4 and performs control for waiting (step S808).

  As described above, according to the control method for the elevator control system according to the present embodiment, the elevator cage 10 can be made to stand by in a timely manner during the time zone in which the boarding / alighting candidate is predicted to board, so that the waiting time of the elevator is shortened. can do.

  Although some embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the spirit of the invention. These embodiments and modifications thereof are included in the scope and the gist of the invention, and are also included in the invention described in the claims and the scope equivalent thereto.

  In the above embodiment, for example, a plurality of elevators may be provided. In this case, for example, a specific boarding / alighting candidate such as the president or an important guest may be registered in the authentication server 3 in advance. Temporarily use one of the elevators as a dedicated passenger for a specific passenger, and at a different time, release the elevator to a passenger other than the specific passenger, and use a dedicated elevator. Do not prepare. As a result, the overall operation efficiency can be improved.

  In the above embodiment, for example, the face of the entry / exit candidate and the floor may be registered in the authentication server 3 in association with each other. Thereby, for example, it is not necessary to physically separate the floors for high floors and low floors, and it is possible to easily know who gets on and off at which floor, so that the elevator can be flexibly operated. For example, if the number of people on the upper floors is overwhelmingly large, it is assumed that the number of elevators going to the upper floors will be increased. A dedicated elevator may be used in combination.

  In the above embodiment, for example, when the predetermined building is an office building, the AI server 4 acquires schedule information such as Outlook (registered trademark) and moves the floor of the entry / exit candidate based on the schedule information. You may predict. As a result, the elevator can be controlled based on more accurate information, and the waiting time of the elevator can be shortened.

  In the above embodiment, for example, when the predetermined building is a hotel, the face of the entry / exit candidate may be registered in the authentication server 3 at the time of check-in. With this, by using face recognition in the elevator, it is possible to stop only the designated floor, and it is possible to secure crime prevention. Currently, in many hotels, a card is used as a key for each room, so there is a risk that the room may be illegally intruded due to forgery or the like. By restricting entry to the elevator, crime prevention can be improved.

  In the above embodiment, the AI server 4 searches for the boarding / alighting candidates to board the elevator before and after the current time based on the stored movement patterns of the boarding / alighting candidates. Therefore, the AI server 4 may predict the number of boarding / alighting candidates of each floor calling the elevator based on the search result, and may automatically move each elevator cage 10 without operating the ascending / descending button.

  In the above embodiment, the elevator car 10 is automatically moved without operating the destination floor button in the elevator car 10. At this time, the destination floor button may be turned on automatically.

  The present invention can also be realized by causing the CPU to execute a computer program, for example, the processing shown in FIG.

  The program can be stored in various types of non-transitory computer readable media and can be supplied to the computer. Non-transitory computer readable media include various types of tangible storage media. Examples of non-transitory computer readable media include magnetic recording media (eg, flexible disk, magnetic tape, hard disk drive), magneto-optical recording media (eg, magneto-optical disk), CD-ROM (Read Only Memory), CD-R, It includes a CD-R / W and a semiconductor memory (for example, mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, RAM (random access memory)).

  The program may be supplied to the computer by various types of transitory computer readable media. Examples of transitory computer-readable media include electrical signals, optical signals, and electromagnetic waves. The transitory computer-readable medium can supply the program to the computer via a wired communication path such as an electric wire and an optical fiber, or a wireless communication path.

1 Elevator Control System 2 Imaging Unit 3 Authentication Server 4 AI Server 5 Elevator Control Unit 10 Elevator Cage

Claims (4)

A photographing means for photographing the passengers getting on and off the elevator of the building,
Recognition means for recognizing the boarding / alighting candidate by performing image authentication of the boarding / alighting candidate based on the image taken by the imaging means;
Learning means for learning, for each of the boarding / alighting candidates, a movement pattern of the boarding / alighting candidate associated with the recognition result of the recognition means and the time information of the boarding / alighting, for each of the boarding / alighting candidates.
A control means for controlling the movement of the elevator based on the movement pattern learned by the learning means,
Based on the movement pattern, the learning means searches for a boarding / alighting candidate to board the elevator before and after the current time, and as a result of the search, the floor where the boarding / alighting candidate is estimated to board at the current time is an elevator cage. Decide on the floor to wait,
Wherein, the floor determined by the learning means, moving the elevator car, have row control to stand,
The recognizing means detects face data from the photographed image transmitted from the photographing means, and when it is determined that the person is not a registered entry / exit candidate, transmits a security risk determination result to the control means,
According to the security risk determination result, the control means performs control so as not to open the door when the entry / exit candidate is in front of the elevator door,
An elevator control system characterized by the above. The elevator control system according to claim 1, wherein
The learning unit, when it is determined that the retrieved passengers are a plurality of passengers, as a result of the search, at the current time, the floor where the number of passengers estimated to board the elevator cage is the largest, Determine the floor on which the elevator car is to wait,
An elevator control system characterized by the above. A step of shooting a boarding / alighting candidate who gets on and off the elevator of the building,
Recognizing the boarding / alighting candidate by performing image authentication of the boarding / alighting candidate based on the photographed image taken,
A step of learning, for each of the boarding / alighting candidates, a movement pattern of the boarding / alighting candidate to each floor in which the recognition result and the time information of the boarding / alighting are associated with each other;
Based on the movement pattern, a boarding / alighting candidate for boarding the elevator before and after the current time is searched, and as a result of the search, a floor where the boarding / alighting candidate is estimated to board at the current time is a floor in which the elevator cage waits. The steps to determine
Moving the elevator car to the determined floor, and performing a control of waiting.
Detecting face data from the captured image and transmitting a security risk determination result when it is determined that the person is not a registered boarding / alighting candidate,
Depending on the transmitted security risk determination result, if the boarding / alighting candidate is in front of the elevator door, a step of performing control so as not to open the door,
An elevator control method comprising: A process of recognizing the boarding / alighting candidate by performing image authentication of the boarding / alighting candidate based on a captured image of the boarding / alighting candidate who gets on and off the elevator of the building,
A process of learning, for each of the boarding / alighting candidates, a movement pattern of the boarding / alighting candidate associated with the recognition result and the time information of the boarding / alighting, to each floor.
Based on the movement pattern, a boarding / alighting candidate for boarding the elevator before and after the current time is searched, and as a result of the search, a floor where the boarding / alighting candidate is estimated to board at the current time is a floor in which the elevator cage waits. Process to determine
A process of moving the elevator car to the determined floor and performing control to make it stand by,
Detecting face data from the photographed image, if it is determined that the person is not a registered boarding / alighting candidate, a process of transmitting a security risk determination result
Depending on the determination result of the transmitted security risk, if the boarding / alighting candidate is in front of the door of the elevator, a process of controlling not to open the door,
A program for an elevator control system, which causes a computer to execute.

Images